Abstract
The spatiotemporal fusion technique has the advantages of generating time-series images with high-spatial and high-temporal resolution from coarse-resolution to fine-resolution images. A hybrid fusion method that integrates image blending (i.e., spatial and temporal adaptive reflectance fusion model, STARFM) and super-resolution (i.e., very deep super resolution, VDSR) techniques for the spatiotemporal fusion of 8 m Formosat-2 and 30 m Landsat-8 satellite images is proposed. Two different fusion approaches, namely Blend-then-Super-Resolution and Super-Resolution (SR)-then-Blend, were developed to improve the results of spatiotemporal fusion. The SR-then-Blend approach performs SR before image blending. The SR refines the image resampling stage on generating the same pixel-size of coarse- and fine-resolution images. The Blend-then-SR approach is aimed at refining the spatial details after image blending. Several quality indices were used to analyze the quality of the different fusion approaches. Experimental results showed that the performance of the hybrid method is slightly better than the traditional approach. Images obtained using SR-then-Blend are more similar to the real observed images compared with images acquired using Blend-then-SR. The overall mean bias of SR-then-Blend was 4% lower than Blend-then-SR, and nearly 3% improvement for overall standard deviation in SR-B. The VDSR technique reduces the systematic deviation in spectral band between Formosat-2 and Landsat-8 satellite images. The integration of STARFM and the VDSR model is useful for improving the quality of spatiotemporal fusion.
Highlights
This study developed a hybrid spatiotemporal image fusion approach involving a deep learning model and a physical model
The deep learning model is the very deep SR (VDSR) model, which improves the spatial resolution of low-resolution images, and the physical model is the spatial and temporal adaptive reflectance fusion model (STARFM) model, which considers physical parameters such as pixel distance, spectral, temporal and spatial variations
In SR-B, SR replaces the image resampling stage used for interpolating the pixel size of a low-resolution image into that of a high-resolution image
Summary
Owing to the availability of remote sensing open data, we have more data sources to construct time-series satellite images. Examples of such data sources are time-series Landsat satellite images provided by the National Aeronautics and Space Administration and time-series. Sentinel satellite images of the European Space Agency (Paris, France). Commercial satellites, such as satellite constellations of Planet Labs, can provide hightemporal-resolution time-series satellite images. The increase in the number of available time-series satellite images has led to the emergence of more diversified applications for the images, such as vegetation phenology detection [1], water resource management [2], rice crop estimation [3], land cover change detection [4], and regional air quality [5]. Time-series satellite image analysis plays an important role in the application of satellite imagery
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
